Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
     "up_proj",
-    "gate_proj",
+    "q_proj",
     "o_proj",
-    "down_proj",
-    "v_proj"
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5dabf2661e207c9b43a2176b759dfaf4afa8ec825724e3e09fe1abaf3ae6c95
+oid sha256:f34f0d9fe7aa143ab5ee8bf3b7c4f5d407047d80a3ef7aad3d1592a58bff822d
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944ac7998997c1f53fcadbef97e09de7d125e7e28d4c71c910e51eff14dd3a08
+oid sha256:c32f74c40694f714d1e1fac09def2f5d44ef7d866c9785417212491c3df8ea26
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85d6e0107c2684f6ba34530e8100ba6b3959f926918734f6ed8e90122f9081d
+oid sha256:24a15dd2d90d035c0c262c0ed9eed0f9b44afdd185709a1e351ea94afecde3a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010482180293501049,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.013626834381551363,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.0010482180293501049,
       "eval_loss": 10.35714054107666,
-      "eval_runtime": 22.1932,
-      "eval_samples_per_second": 18.114,
+      "eval_runtime": 22.194,
+      "eval_samples_per_second": 18.113,
       "eval_steps_per_second": 9.057,
       "step": 1
+    },
+    {
+      "epoch": 0.005241090146750524,
+      "grad_norm": 10.603066444396973,
+      "learning_rate": 5e-05,
+      "loss": 10.5321,
+      "step": 5
+    },
+    {
+      "epoch": 0.010482180293501049,
+      "grad_norm": 6.600972652435303,
+      "learning_rate": 0.0001,
+      "loss": 9.7309,
+      "step": 10
+    },
+    {
+      "epoch": 0.010482180293501049,
+      "eval_loss": 9.703192710876465,
+      "eval_runtime": 22.2818,
+      "eval_samples_per_second": 18.042,
+      "eval_steps_per_second": 9.021,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 121751532994560.0,
+  "total_flos": 1339266862940160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87fc6d570efa54666c559aa77c55cadf789c31e7d11949236286bc5e64dd0dea
+oid sha256:fc9dbf32e2b7b8f22d19fe043d53d81fd7fba22ed3d8dd60211ee97ae13fb0cf
 size 6776